Aircraft flight parameter detection based on a neural network using multiple hot-film flow speed sensors

Air speed, the angle of attack and the angle of sideslip are fundamental parameters in the control of flying bodies. Conventional detection techniques use sensors that may protrude outside the aircraft and be too bulky and intrusive for small unmanned air vehicles and micro air vehicles. In this paper, a novel and practical methodology by which the flight parameters are inferred from multiple hot-film flow speed sensors mounted on the surface of the wing is presented. In order to get a good mathematical relation between the readings of the sensors and the flight parameters, we use a back-propagation neural network to model the relationship. The methodology is validated by wind tunnel experiments, and the experimental results are presented.